{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H36SJFJIZ5FQJO7YFOWBURMWFJ","short_pith_number":"pith:H36SJFJI","canonical_record":{"source":{"id":"2502.19941","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T10:11:53Z","cross_cats_sorted":[],"title_canon_sha256":"9714f5e870d9dc62edd2256fb68ea4e3cf2c7a10e9f9c4eb16582ef402552245","abstract_canon_sha256":"33642ebd2989a9217427ea223efd0862e35773b32795ccee509dcf11a3fb2eaa"},"schema_version":"1.0"},"canonical_sha256":"3efd249528cf4b04bbf82bac1a45962a5dfcfc4704985b8fc5668557c087b8f4","source":{"kind":"arxiv","id":"2502.19941","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19941","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19941v3","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19941","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"H36SJFJIZ5FQ","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"H36SJFJIZ5FQJO7Y","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"H36SJFJI","created_at":"2026-07-05T11:23:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H36SJFJIZ5FQJO7YFOWBURMWFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.19941","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T10:11:53Z","cross_cats_sorted":[],"title_canon_sha256":"9714f5e870d9dc62edd2256fb68ea4e3cf2c7a10e9f9c4eb16582ef402552245","abstract_canon_sha256":"33642ebd2989a9217427ea223efd0862e35773b32795ccee509dcf11a3fb2eaa"},"schema_version":"1.0"},"canonical_sha256":"3efd249528cf4b04bbf82bac1a45962a5dfcfc4704985b8fc5668557c087b8f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:23.686503Z","signature_b64":"RK3DLU39gO1rfUKhA3YFLigdtZeZ1DkWZG4HFY1cpmPEq3n9D4KHrUm6GR9IGpQvioxp6qJy0Fs6HrhIpXgnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3efd249528cf4b04bbf82bac1a45962a5dfcfc4704985b8fc5668557c087b8f4","last_reissued_at":"2026-07-05T11:23:23.685990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:23.685990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.19941","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A4y+neg3aYly3wQqI6JLUCwesMpVFywMFpEvXHuA/69ei67F24FhSevUjrCR76bwQ69xWC6Ws3j7uxaiK3fJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:38:01.794916Z"},"content_sha256":"da87c7f2f97c8416d384df688c184b7bc8a285aa01492959310b28586b9bb215","schema_version":"1.0","event_id":"sha256:da87c7f2f97c8416d384df688c184b7bc8a285aa01492959310b28586b9bb215"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H36SJFJIZ5FQJO7YFOWBURMWFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiajun Chen, Shujian Huang, Xiang Geng, Zhejian Lai","submitted_at":"2025-02-27T10:11:53Z","abstract_excerpt":"Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task. Due to the data scarcity, synthetic data generation has emerged as a promising solution. However, synthetic QE data often suffers from distribution shift, which can manifest as discrepancies between pseudo and real translations, or in pseudo labels that do not align with human preferences. To tackle this issue, we introduce DCSQE, a novel framework for alleviating distribution shift in synthetic QE data. To reduce the difference betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19941","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.19941/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"41JQpfbQw/Xa4TIobh8PilUofxfuW9Jlho76bSwrS3Dx5b+wExTUMf86aNBe24abPxElp2ilibVO2afxmm/XCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:38:01.795455Z"},"content_sha256":"15cce8471684f7805a980ad7f8ec1e162add1b41579dadaa966931453935e177","schema_version":"1.0","event_id":"sha256:15cce8471684f7805a980ad7f8ec1e162add1b41579dadaa966931453935e177"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H36SJFJIZ5FQJO7YFOWBURMWFJ/bundle.json","state_url":"https://pith.science/pith/H36SJFJIZ5FQJO7YFOWBURMWFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H36SJFJIZ5FQJO7YFOWBURMWFJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T07:38:01Z","links":{"resolver":"https://pith.science/pith/H36SJFJIZ5FQJO7YFOWBURMWFJ","bundle":"https://pith.science/pith/H36SJFJIZ5FQJO7YFOWBURMWFJ/bundle.json","state":"https://pith.science/pith/H36SJFJIZ5FQJO7YFOWBURMWFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H36SJFJIZ5FQJO7YFOWBURMWFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H36SJFJIZ5FQJO7YFOWBURMWFJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"33642ebd2989a9217427ea223efd0862e35773b32795ccee509dcf11a3fb2eaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T10:11:53Z","title_canon_sha256":"9714f5e870d9dc62edd2256fb68ea4e3cf2c7a10e9f9c4eb16582ef402552245"},"schema_version":"1.0","source":{"id":"2502.19941","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19941","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19941v3","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19941","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"H36SJFJIZ5FQ","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"H36SJFJIZ5FQJO7Y","created_at":"2026-07-05T11:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"H36SJFJI","created_at":"2026-07-05T11:23:23Z"}],"graph_snapshots":[{"event_id":"sha256:15cce8471684f7805a980ad7f8ec1e162add1b41579dadaa966931453935e177","target":"graph","created_at":"2026-07-05T11:23:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.19941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task. Due to the data scarcity, synthetic data generation has emerged as a promising solution. However, synthetic QE data often suffers from distribution shift, which can manifest as discrepancies between pseudo and real translations, or in pseudo labels that do not align with human preferences. To tackle this issue, we introduce DCSQE, a novel framework for alleviating distribution shift in synthetic QE data. To reduce the difference betw","authors_text":"Hao Yang, Jiajun Chen, Shujian Huang, Xiang Geng, Zhejian Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T10:11:53Z","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19941","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:da87c7f2f97c8416d384df688c184b7bc8a285aa01492959310b28586b9bb215","target":"record","created_at":"2026-07-05T11:23:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"33642ebd2989a9217427ea223efd0862e35773b32795ccee509dcf11a3fb2eaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T10:11:53Z","title_canon_sha256":"9714f5e870d9dc62edd2256fb68ea4e3cf2c7a10e9f9c4eb16582ef402552245"},"schema_version":"1.0","source":{"id":"2502.19941","kind":"arxiv","version":3}},"canonical_sha256":"3efd249528cf4b04bbf82bac1a45962a5dfcfc4704985b8fc5668557c087b8f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3efd249528cf4b04bbf82bac1a45962a5dfcfc4704985b8fc5668557c087b8f4","first_computed_at":"2026-07-05T11:23:23.685990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:23.685990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RK3DLU39gO1rfUKhA3YFLigdtZeZ1DkWZG4HFY1cpmPEq3n9D4KHrUm6GR9IGpQvioxp6qJy0Fs6HrhIpXgnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:23.686503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19941","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da87c7f2f97c8416d384df688c184b7bc8a285aa01492959310b28586b9bb215","sha256:15cce8471684f7805a980ad7f8ec1e162add1b41579dadaa966931453935e177"],"state_sha256":"f84f38e8bc5aaf22ea3dd76e2d7d949bc138ad4d97f2ac17d2d9ecdb8d854c32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nwKHoDs1qwcQa4yZhnGpqQvH4JIfqEJ82FIzNVnn3uQBOWayo2+mcrv+oi2iwJB7j+c1QNaaWQQp/KeN25lUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:38:01.800826Z","bundle_sha256":"f2be67cb35a2ccf15e0cfa168d46eda5be3b762810f1b5cd0d51f8fbd712eca4"}}